projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 84aa1d3) | patch
[neurun] Fix fining scheduler and tryBackend (#6616)
authorДилшоджон Пошшоев/AI Tools Lab /SRR/Engineer/삼성전자 <d.poshshoev@samsung.com>
Wed, 14 Aug 2019 09:17:02 +0000 (12:17 +0300)
committer이한종/On-Device Lab(SR)/Engineer/삼성전자 <hanjoung.lee@samsung.com>
Wed, 14 Aug 2019 09:17:02 +0000 (18:17 +0900)
commitd47b97eb5609c2fcfd8b9e9e473ea1c73c159b68
tree8a36972fb5e9eaa9f26df3093c0df40183f79aa4tree | snapshot
parent84aa1d306351ec15b4ec4d91a5410cc943210b1dcommit | diff
[neurun] Fix fining scheduler and tryBackend (#6616)

CPU_DELAY must be just for parallel executor.
Also tryBackend: PR 5894  commented a line and this
reduced performance by 10%

Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
runtimes/neurun/core/src/compiler/Scheduler.cc diff | blob | history
Domain: Machine Learning / ML Framework;